No install? Use cloud.anythingmcp.com directly.
Sign in, install the YouTube Data API in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Read YouTube data — videos, channels, playlists, search, comments — and (with OAuth) manage your own uploads. 9 tools, API key + optional OAuth Bearer.
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → YouTube Data API、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
YouTube Data API + Gemini
Read YouTube data — videos, channels, playlists, search, comments — and (with OAuth) manage your own uploads. 9 tools, API key + optional OAuth Bearer.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
YOUTUBE_API_KEY
步骤 1 — 获取凭证
google.com/youtube/v3).
Setup:
- Create / pick a Google Cloud project at https://console.cloud.google.com.
- APIs & Services → Library → enable YouTube Data API v3.
- Credentials → Create credentials → API key. (For write operations, also do OAuth2 client + get a Bearer token with
youtube.upload/youtubescopes — out of scope here.) - Set
YOUTUBE_API_KEYto the API key.
Authentication: query-string ?key=.... Read operations don't need OAuth.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—YouTube Data API应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
youtube_search | Search videos / channels / playlists |
youtube_get_videos | Fetch video details by ID(s) |
youtube_get_videos_chart | Get videos from a chart (currently only 'mostPopular') |
youtube_get_channels | Fetch channel details by ID, handle (@username), forUsername (legacy), or 'mine' (requires OAuth) |
youtube_list_playlists | List playlists, filtered by channelId or 'mine' (OAuth) |
youtube_list_playlist_items | List items in a playlist (videos in playlist) |
youtube_list_video_comments | List top-level comments on a video |
youtube_list_categories | List video categories for a region |
youtube_get_captions | List caption tracks available for a video |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对您有帮助吗?